Sohyun An

Sohyun An

PhD student at UCLA

UCLA CS

Biography

I’m a Ph.D. student in the Computational Machine Learning Group at UCLA, under the supervision of Prof. Cho-Jui Hsieh. Previously, I was an M.S. student in the Machine Learning and Artificial Intelligence (MLAI) Lab at KAIST AI, supervised by Prof. Sung Ju Hwang.

I am interested in developing machine learning algorithms to foster the AI-based application ecosystem. I believe this goal can be achieved by efficiently & effectively solving tasks using various search and optimization techniques within a defined search space, while also ensuring that these algorithms are applicable to real-world scenarios.

Recent News

  • May 2024 : πŸŽ‰ One paper accepted to ICML 2024.
  • Mar 2024 : ✈️ Travel Grant for ICLR 2024 from ICLR Organizers.
  • Jan 2024 : πŸŽ‰ One paper accepted to ICLR 2024.
  • Jul 2023 : ✈️ Travel Grant for AutoML 2023 from AutoML Organizers.
  • Apr 2023 : ✈️ Google Travel Grant for ICLR 2023 from Google.
  • Jan 2023 : πŸŽ‰ One paper accepted to ICLR 2023 as Notable-top-25% - Spotlight Presentation.
Interests
  • Generative Models / LLMs
  • Search / Optimization
  • AutoML / Meta-learning
Education
  • PhD in Computer Science, Sep 2024 - Present

    University of California, Los Angeles (UCLA)

  • MS in Artificial Intelligence, Aug 2022 - Aug 2024

    Korea Advanced Institute of Science and Technology (KAIST)

  • BS in Material Science and Engineering (Summa Cum Laude), Mar 2017 - Aug 2021

    Seoul National University (SNU)

Publications

Quickly discover relevant content by filtering publications.
(2024). One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts. ICML 2024.

Cite PDF

(2024). DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models. ICLR 2024.

Cite PDF Code

(2023). Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets. ICLR 2023, Spotlight (notable-top-25%).

Cite PDF Code

(2022). Lightweight Neural Architecture Search with Parameter Remapping and Knowledge Distillation. AutoML 2022 Workshop.

Cite PDF

Experience

 
 
 
 
 
Research Intern
April 2021 – August 2021 South Korea
Conducted research on AutoML, Neural Architecture Search, and Meta-learning.
 
 
 
 
 
Full-time Engineer
August 2021 – March 2022 South Korea
Worked on Advanced Packaging of High Bandwidth Memory (HBM).
 
 
 
 
 
Undergraduate Student Researcher
January 2020 – September 2020 South Korea
Conducted research on ‘The Effect of Resistance Drift of Phase Change Memory on Artificial Neural Networks.
 
 
 
 
 
Engineer Intern
June 2019 – August 2019 South Korea
Worked on DRAM circuit design at Tech Core Design Team.

Projects

AutoML with Large-scale Hyperparameter Meta-Learning

TA Experience

 
 
 
 
 
SNS TA
September 2023 – December 2023 South Korea
 
 
 
 
 
TA for AI618 Generative Model and Unsupervised Learning
March 2023 – June 2023 South Korea

Contact